# FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting

arXiv: https://arxiv.org/abs/2512.03369 · HTML: https://mlsanity.com/paper/2512.03369/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 32 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Builds on (most cited first, 3 of 3)

- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [STDiff: Spatio-temporal Diffusion for Continuous Stochastic Video Prediction](https://mlsanity.com/paper/2312.06486/) (2023)
- [30m resolution Global Annual Burned Area Mapping based on Landsat images and Google Earth Engine](https://mlsanity.com/paper/1805.02579/) (2018)

## Built on by (most cited first, 3 of 3)

- [DisasterBench: A Multimodal Benchmark for UAV-Based Disaster Response in Complex Environments](https://mlsanity.com/paper/2606.06217/) (2026)
- [N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting](https://mlsanity.com/paper/2603.07361/) (2026)
- [SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs](https://mlsanity.com/paper/2609.07823/) (2026)

## Abstract (arXiv)

Fine-grained wildfire spread prediction is crucial for enhancing emergency response efficacy and decision-making precision. However, existing research predominantly focuses on coarse spatiotemporal scales and relies on low-resolution satellite data, capturing only macroscopic fire states while fundamentally constraining high-precision localized fire dynamics modeling capabilities. To bridge this gap, we present FireSentry, a provincial-scale multi-modal wildfire dataset characterized by sub-meter spatial and sub-second temporal resolution. Collected using synchronized UAV platforms, FireSentry provides visible and infrared video streams, in-situ environmental measurements, and manually validated fire masks. Building on FireSentry, we establish a comprehensive benchmark encompassing physics-based, data-driven, and generative models, revealing the limitations of existing mask-only approaches. Our analysis proposes FiReDiff, a novel dual-modality paradigm that first predicts future video sequences in the infrared modality, and then precisely segments fire masks in the mask modality based on the generated dynamics. FiReDiff achieves state-of-the-art performance, with video quality gains of 39.2% in PSNR, 36.1% in SSIM, 50.0% in LPIPS, 29.4% in FVD, and mask accuracy gains of 3.3% in AUPRC, 59.1% in F1 score, 42.9% in IoU, and 62.5% in MSE when applied to generative models. The FireSentry benchmark dataset and FiReDiff paradigm collectively advance fine-grained wildfire forecasting and dynamic disaster simulation. The processed benchmark dataset is publicly available at: https://github.com/Munan222/FireSentry-Benchmark-Dataset.